© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129570
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     จาก
    -0.08
     GG
    -0.08
     blessures
    -0.07
    Instructor
    -0.07
     impending
    -0.07
    cha
    -0.07
    届け
    -0.07
     преподав
    -0.07
     чтобы
    -0.07
    老师
    -0.07
    POSITIVE LOGITS
    ^{-
    0.11
    702
    0.08
     sod
    0.08
    ^{
    0.08
    102
    0.08
    195
    0.07
    ুম
    0.07
     mith
    0.07
    555
    0.07
    673
    0.07
    Activations Density 0.097%

    No Known Activations